检索结果-内蒙古大学图书馆

Security-Enhanced Data Sharing Via Efficient Sanitization for VANETs

IEEE Transactions on Mobile computing 2025年第6期24卷 4925-4938页

作者： Zhong, Hong Zhou, Dan Cui, Jie Wang, Li Zhang, Jing Bolodurina, Irina He, Debiao Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Hefei230039 China Anhui University Anhui Engineering Laboratory of IoT Security Technologies Hefei230039 China Orenburg State University Faculty of Mathematics and Information Technologies Orenburg460018 Russia Wuhan University School of Cyber Science and Engineering Wuhan430072 China MatrixElements Technologies Shanghai Key Laboratory of Privacy Preserving Computation Shanghai201204 China

With the widespread deployment of vehicular ad-hoc networks (VANETs), data sharing has garnered considerable attention as a core feature of VANETs. Attribute-based proxy re-encryption (ABPRE) enables fine-grained access control and provides flexible ciphertext updates. The initially authorized vehicle generates the re-encryption key to enable ciphertext-to-ciphertext conversion in the cloud, allowing ciphertext to be shared with new recipients. However, initially authorized vehicles may not always be trustworthy and could share data with malicious receivers. In addition, the computation and communication overhead of ABPRE hinders its widespread application in VANETs. To address these issues, we propose a lightweight sanitizable scheme for edge-assisted VANETs based on ABPRE. In this scheme, the re-encryption key is verified by a sanitizer, to prevent the data from being shared with malicious data receivers. In addition, key-splitting techniques and edge computing are employed to reduce the communication and computation overhead of re-encryption. A comprehensive security analysis and performance evaluation demonstrate that the proposed scheme is efficient and practical. © 2002-2012 IEEE.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

On the Performance of Active RIS-Assisted Mixed RF-THz Relaying Systems

引用

IEEE Internet of Things Journal 2025年第10期12卷 14938-14951页

作者： Yin, Yiyang Yang, Liang Li, Xingwang Liu, Hongwu Guo, Kefeng Li, Yingsong Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454000 China Shandong Jiaotong University School of Information Science and Electrical Engineering Jinan250357 China Space Engineering University School of Space Information Beijing101407 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China

We investigate the performance of an active reconfigurable intelligent surface (RIS)-assisted mixed radio frequency (RF)-terahertz (THz) relaying system, where the RF signal reaches the relay through the active RIS and is then transmitted to the user via the THz channel. Under this scenario, we analyze the system performance with the relay employing amplify-and-forward (AF) and decode-and-forward (DF) protocols. More specifically, we derive the exact expressions for the cumulative distribution function (CDF) of the end-to-end signal-to-noise ratio (SNR) for both relaying protocols. Based on this, we obtain the exact expressions for the outage probability, average bit error rate (ABER), and average channel capacity (ACC). Furthermore, to gain deeper insights, we derive the asymptotic expressions at high SNRs and obtain diversity order (DO) of the system. Moreover, we extend the analysis to the variable gain relaying scheme. The findings reveal that the DOs for both relaying protocols are determined by the THz channel parameters, and the DO under the AF relaying protocol is twice that of the DF relaying protocol. Finally, we validate that active RIS (A-RIS) can more effectively assist the performance of the mixed RF-THz relaying system compared to passive RIS. © 2014 IEEE.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Recipe Generation

Retrieval Augmented Recipe Generation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Guoshan Liu Hailong Yin Bin Zhu Jingjing Chen Chong-Wah Ngo Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Singapore Management University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset.

关键词： Training Computer vision Accuracy Computational modeling Stochastic processes Predictive models Reliability Faces

来源：评论

学校读者我要写书评

暂无评论

Domain-aware Node Representation Learning for Graph Out-of-Distribution Generalization

Domain-aware Node Representation Learning for Graph Out-of-D...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yi Qiao Yang Liu Qing He Xiang Ao Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciencs Beijing China Institute of Intelligent Computing Technology Suzhou CAS

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph Neural Networks (GNNs) have demonstrated impressive success across diverse fields when data satisfies in-distribution (ID) assumption. Nevertheless, GNN performance significantly declines in cases of distribution shifts between training and testing graph data. This degradation primarily stems from spurious correlations between irrelevant domain information and target labels in out-of-distribution (OOD) scenarios. Thus, maximizing the utilization of domain information becomes imperative. In light of this, we propose a novel approach named Domain-aware Node Representation Learning (DNRL), comprehensively incorporates domain information to bolster generalization capability. Specifically, DNRL selectively interpolates nodes with the same label but different domains, extending training data into unseen domains and alleviating the effects caused by domain-related spurious correlations. Futhermore, by introducing a domain-aware contrastive learning strategy, our method implicitly decouples domain information from node information to learn domain-independent node representations. Extensive experiments on graph out-of-distribution benchmarks demonstrate that DNRL can achieve effective OOD generalization performance across diverse domains.

关键词： Representation learning Training Degradation Interpolation Correlation Training data signal processing Graph neural networks Data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

A Tetrahedral Spectral Element Method for Thermo-Mechanical Analysis of Electronic Devices

引用

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Feng, Naixing Zhang, Shuai Huang, Zhixiang Liu, Qi Qiang Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes Hefei China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou310018 China

For the coupled thermo-mechanical simulation of complex electronic devices, we propose a Tetrahedral Spectral Element Method (TSEM), which truly combines the high accuracy of spectral methods with the strong geometric adaptability of Finite Element Methods (FEMs). The TSEM employs a collapse transformation method and successfully converts the orthogonal Gauss-Lobatto-Legendre (GLL) basis functions from a hexahedron to a tetrahedral reference element. This ensures numerical accuracy and stability for arbitrary high-order interpolation. We also generate non-equidistant GLL spectral interpolation nodes for tetrahedral elements through Warp&Blend transformation, enabling direct nodal numerical integration calculation through Vandermonde matrices. This approach replaces the classical Gaussian quadrature in the FEM, not only significantly enhancing the computational efficiency of element matrix but also avoiding potential numerical dissipation and dispersion associated with Gaussian integration, thus achieving rapid convergence. In the TSEM thermo-mechanical coupling, we further construct a separate solver based on the implicit Newmark-β method, which realizes unconditional stability for temporal integration for arbitrary time step increment. Moreover, it supports independent inversion of system matrices for temperature and stress fields, without increasing computational resource consumption due to the coupling of multi-physics equations. By quantitatively comparing with the COMSOL Multiphysics software, several typical case studies are used to demonstrate the significant advantages of the TSEM in numerical accuracy, efficiency, and stability. © 2025 IEEE. All rights reserved.

关键词： Orthogonal functions

来源：评论

学校读者我要写书评

暂无评论

A Nonconformal SETI-DP Method for Transient Thermal Simulation

引用

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Feng, Naixing Li, Hongyang Huang, Zhixiang Liu, Qi Qiang Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The Information Materials and Intelligent Sensing Laboratory of Anhui Province The Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes Hefei China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou310018 China

This paper proposes a novel nonconformal meshbased dual-primal spectral element tearing and interconnecting (SETI-DP) method designed for the efficient transient simulation of complex large-scale heat conduction problems utilizing a domain decomposition method (DDM). This method allows for the division of complex, large-scale problems into smaller subdomain problems. By applying Robin-type transmission conditions at the subdomain interfaces, rapid convergence of the global interface iterative solution is achieved for arbitrary non-conformal subdomain problems. This non-conformal DDM approach supports independent meshing of subdomains, eliminating the need to generate a globally continuous mesh for large-scale problems, thereby significantly enhancing meshing efficiency. In addition, this non-conformal meshing strategy enables high-contrast spatial discretization and mixed-order spectral interpolation between different subdomains. This significantly increases meshing flexibility, minimizes the number of degrees of freedom (DoF) in multi-scale problems, and reduces computational costs. In addition, by developing a subdomain-coupled time iteration scheme, the global corner problem of residual transfer is explicitly given, which greatly improves the versatility and flexibility of the algorithm. Finally, to demonstrate the accuracy, efficiency, and robustness of our algorithm, we conduct benchmark tests on several representative examples. © 2011-2012 IEEE.

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference

Attacking Voice Anonymization Systems with Augmented Feature...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yanzhe Zhang Zhonghao Bi Feiyang Xiao Xuefeng Yang Qiaoxi Zhu Jian Guan Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University China Faculty of Computing Harbin Institute of Technology China Acoustics Lab University of Technology Sydney Australia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This study focuses on the First VoicePrivacy Attacker Challenge within the ICASSP 2025 signal processing Grand Challenge, which aims to develop speaker verification systems capable of determining whether two anonymized speech signals are from the same speaker. However, differences between feature distributions of original and anonymized speech complicate this task. To address this challenge, we propose an attacker system that combines Data Augmentation enhanced feature representation and Speaker Identity Difference enhanced classifier to improve verification performance, termed DA-SID. Specifically, data augmentation strategies (i.e., data fusion and SpecAugment) are utilized to mitigate feature distribution gaps, while probabilistic linear discriminant analysis (PLDA) is employed to further enhance speaker identity difference. Our system significantly outperforms the baseline, demonstrating exceptional effectiveness and robustness against various voice anonymization systems, ultimately securing a top-5 ranking in the challenge.

关键词： Data privacy Data integration signal processing Data augmentation Probabilistic logic Robustness Linear discriminant analysis Information filtering Speech processing Information integrity

来源：评论

学校读者我要写书评

暂无评论

BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers

arXiv

引用

arXiv 2025年

作者： Zhang, Hui Gao, Tingwei Shao, Jie Wu, Zuxuan Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China ByteDance Intelligent Creation China

Diffusion models have demonstrated impressive generation capabilities, particularly with recent advancements leveraging transformer architectures to improve both visual and artistic quality. However, Diffusion Transformers (DiTs) continue to encounter challenges related to low inference speed, primarily due to the iterative denoising process. To address this issue, we propose BlockDance, a training-free approach that explores feature similarities at adjacent time steps to accelerate DiTs. Unlike previous feature-reuse methods that lack tailored reuse strategies for features at different scales, BlockDance prioritizes the identification of the most structurally similar features, referred to as Structurally Similar Spatio-Temporal (STSS) features. These features are primarily located within the structure-focused blocks of the transformer during the later stages of denoising. BlockDance caches and reuses these highly similar features to mitigate redundant computation, thereby accelerating DiTs while maximizing consistency with the generated results of the original model. Furthermore, considering the diversity of generated content and the varying distributions of redundant features, we introduce BlockDance-Ada, a lightweight decision-making network tailored for instance-specific acceleration. BlockDance-Ada dynamically allocates resources and provides superior content quality. Both BlockDance and BlockDance-Ada have proven effective across various generation tasks and models, achieving accelerations between 25% and 50% while maintaining generation quality. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A contrastive learning framework of graph reconstruction and hypergraph learning for key node identification

引用

Chaos, Solitons and Fractals 2025年 197卷

作者： Huang, Xu-Dong Zhang, Xian-Jie Zhang, Hai-Feng Data Intelligence Lab Research Center For Data To Cyberspace School of Cyber Science and Technology University of Science and Technology of China Hefei Anhui230026 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui University Hefei Anhui230601 China

With the emergence of complex networks in various domains, the key node identification has become one of the critical issues that needs to be studied. Traditional index methods typically focus on single structural information, while existing data-driven approaches often rely solely on the intrinsic lower-order features of nodes. However, assessing the importance of nodes requires a comprehensive consideration of both network structures and higher-order features from multiple perspectives. To address these challenges, this paper proposes a novel deep learning framework based on Graph Reconstruction and Hypergraph Contrastive Learning, termed GRHCL. The GRHCL method constructs hypergraph structures from original graphs using random walks, followed by leveraging graph reconstruction and hypergraph learning methods to capture both structural and higher-order embedding features of nodes. Positive and negative node pairs are then constructed across different views for contrastive learning. Finally, the model is trained using a training sample set obtained through a clustering sampling strategy, along with a joint loss function. Comparative experiments against various baseline methods demonstrate that the GRHCL method achieves superior predictive performance with smaller training sets, improving accuracy by over 5% on some datasets compared to the next best-performing method. © 2025 Elsevier Ltd

关键词： Clustering sampling Contrastive learning Graph reconstruction learning Hypergraph learning key node identification

来源：评论

学校读者我要写书评

暂无评论

Predicting Calibrated Conversion Rate of Online Advertising Using a Multi-task Mixture-of-Experts Calibration Model 12th

Predicting Calibrated Conversion Rate of Online Advertising...

引用

12th CCF Conference on BigData, BigData 2024

作者： Zhang, Xinyue Guo, Yuyao Ao, Xiang School of Information Engineering China University of Geosciences Beijing China Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China

ISBN: (纸本)9789819610235

Accurately predicting conversion rate (CVR) is paramount in online advertising. However, traditional models may face problems such as delayed feedback, where there is a delay of an indeterminate amount of time between click and conversion. Calibration is an effective way to optimize conversion rate estimates in online advertising. Unlike conversion delays, post-click user behaviors occur rapidly and are informative to conversion rate prediction. Our proposed solution, the Multi-Task Mixture-of-Experts Calibration (MTMEC) framework, integrates multi-task learning and mixture-of-experts models. It modifies CVR prediction using post-click user behavior data, utilizing streaming learning for real-time data access. Each task is weighted by a gating network, enabling adaptive loss functions through multi-task learning. Parametric scaling further minimizes calibration errors, enhancing prediction accuracy without excessive parameters. Experiments on real-world datasets validate the effectiveness of MTMEC. It improves model prediction and reduces calibration errors. This framework offers a robust solution for online advertising, bridging the gap between calibration accuracy and system responsiveness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：